mlsanityData to 14 Oct 2026

Lavida-O: Elastic Large Masked Diffusion Models for Unified Multimodal Understanding and Generation

arXiv 2509.19244 ↗First posted 23 Sep 2025cs.CVcited by 15

On the map: Diffusion models → Image generation, text-to-image and editing

Abstract (arXiv)

We propose Lavida-O, a unified Masked Diffusion Model (MDM) for multimodal understanding and generation. Unlike existing multimodal MDMs such as MMaDa and Muddit which only support simple image-level understanding tasks and low-resolution image generation, Lavida-O presents a single framework that enables image-level understanding, object grounding, image editing, and high-resolution (1024px) text-to-image synthesis. Lavida-O incorporates a novel Elastic Mixture-of-Transformers (Elastic-MoT) architecture that couples a lightweight generation branch with a larger understanding branch, supported by token compression, universal text conditioning and stratified sampling for efficient and high-quality generation. Lavida-O further incorporates planning and iterative self-reflection in image generation and editing tasks, seamlessly boosting generation quality with its understanding capabilities. Lavida-O achieves state-of-the-art performance on a wide range of benchmarks including RefCOCO object grounding, GenEval text-to-image generation, and ImgEdit image editing, outperforming existing autoregressive models and continuous diffusion models such as Qwen2.5-VL and FluxKontext-dev, while offering considerable speedup at inference. These advances establish Lavida-O as a new paradigm for scalable multimodal reasoning and generation.

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models. Builds on 73 of its 85 references that are in the map. First posted on arXiv 23 Sep 2025.

Builds on

73 of 85 references.

Closest ancestors · 13

Same direction, newest first

  1. 2025FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space17 Jun
  2. 2025Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model29 May
  3. 2025LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuning22 May
  4. 2025LaViDa: A Large Diffusion Language Model for Multimodal Understanding22 May
  5. 2025BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset14 May
  6. 2025From Reflection to Perfection: Scaling Inference-Time Optimization for Text-to-Image Diffusion Models via Reflection Tuning22 Apr
  7. 2025Reflect-DiT: Inference-Time Scaling for Text-to-Image Diffusion Transformers via In-Context Reflection15 Mar
  8. 2024Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis10 Oct
  9. 2024OmniGen: Unified Image Generation17 Sep
  10. 2024ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment8 Mar
  11. 2023GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment17 Oct
  12. 2022Unified Discrete Diffusion for Simultaneous Vision-Language Generation27 Nov
1 more
  1. 2022InstructPix2Pix: Learning to Follow Image Editing Instructions17 Nov

Other references · 60

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2023Segment Anythingcited by 8,234
  5. 2025Qwen2.5-VL Technical Reportcited by 5,587
  6. 2024GPT-4o System Cardcited by 4,588
  7. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
  8. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
  9. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,152
  10. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,332
  11. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,253
  12. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,109
38 more
  1. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 2,719
  2. 2023MMBench: Is Your Multi-modal Model an All-around Player?cited by 2,141
  3. 2023MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGIcited by 2,080
  4. 2022Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answeringcited by 1,919
  5. 2025InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Modelscited by 1,834
  6. 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,719
  7. 2023MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Modelscited by 1,652
  8. 2023MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contextscited by 1,614
  9. 2022ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoningcited by 1,479
  10. 2020DocVQA: A Dataset for VQA on Document Imagescited by 1,317
  11. 2022MaskGIT: Masked Generative Image Transformercited by 1,099
  12. 2016Modeling Context in Referring Expressionscited by 1,063
  13. 2025Large Language Diffusion Modelscited by 912
  14. 2015Generation and Comprehension of Unambiguous Object Descriptionscited by 904
  15. 2025Emerging Properties in Unified Multimodal Pretrainingcited by 897
  16. 2023Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesiscited by 890
  17. 2024Simple and Effective Masked Diffusion Language Modelscited by 848
  18. 2025Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scalingcited by 812
  19. 2024Show-o: One Single Transformer to Unify Multimodal Understanding and Generationcited by 752
  20. 2023Discrete Diffusion Modeling by Estimating the Ratios of the Data Distributioncited by 745
  21. 2023Muse: Text-To-Image Generation via Masked Generative Transformerscited by 648
  22. 2024Simplified and Generalized Masked Diffusion for Discrete Datacited by 626
  23. 2023MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editingcited by 624
  24. 2023GLaMM: Pixel Grounding Large Multimodal Modelcited by 455
  25. 2025Step1X-Edit: A Practical Framework for General Image Editingcited by 429
  26. 2025Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decodingcited by 420
  27. 2022Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentationcited by 344
  28. 2024UltraEdit: Instruction-based Fine-Grained Image Editing at Scalecited by 268
  29. 2023T2I-CompBench++: An Enhanced and Comprehensive Benchmark for Compositional Text-to-image Generationcited by 260
  30. 2024AnyEdit: Mastering Unified High-Quality Image Editing for Any Ideacited by 241
  31. 2025Transfer between Modalities with MetaQueriescited by 236
  32. 2025ImgEdit: A Unified Image Editing Dataset and Benchmarkcited by 231
  33. 2023JourneyDB: A Benchmark for Generative Image Understandingcited by 205
  34. 2022mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connectionscited by 187
  35. 2025SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformercited by 165
  36. 2024Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Modelscited by 163
  37. 2024MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scalecited by 127
  38. 2024LMFusion: Adapting Pretrained Language Models for Multimodal Generationcited by 120

50 most cited of 60 All 60 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 11.

15 papers.

Sort:

By area:

  1. 2026InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editingcited by 28
  2. 2025Dream-VL & Dream-VLA: Open Vision-Language and Vision-Language-Action Models with Diffusion Language Model Backbonecited by 18
  3. 2025HBridge: H-Shape Bridging of Heterogeneous Experts for Unified Multimodal Understanding and Generationcited by 11
  4. 2026LaViDa-R1: Advancing Reasoning for Unified Multimodal Diffusion Language Modelscited by 7
  5. 2025Sparse-LaViDa: Sparse Multimodal Discrete Diffusion Language Modelscited by 6
  6. 2025From Masks to Worlds: A Hitchhiker's Guide to World Modelscited by 5
  7. 2026Dynin-Omni: Omnimodal Unified Large Diffusion Language Modelcited by 5
  8. 2026SNCE: Geometry-Aware Supervision for Scalable Discrete Image Generationcited by 1
  9. 2026Sketch Then Paint: Hierarchical Reinforcement Learning for Diffusion Multi-Modal Large Language Modelscited by 1
  10. 2026Illuminating Unified Multimodal Model for Free-form Interleaved Text-Image Generationcited by 1
  11. 2026Guidance Contrastive Token Credit Assignment for Discrete Policy Optimizationcited by 0
  12. 2026Nemotron-Labs-Diffusion-Image: Advancing Masked Discrete Diffusion for High-Resolution Image Synthesiscited by 0
3 more
  1. 2026Discrete Diffusion Bridges for Spatiotemporally Aligned Image Translation and Generationcited by 0
  2. 2026Dynin-Robotics: Omnimodal Unified Diffusion Vision-Language-Action Modelcited by 0
  3. 2026Making Language the Low-Rate Code of Vision: Successive Refinement from Words to Pixelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025MammothModa2: A Unified AR-Diffusion Framework for Multimodal Understanding and Generation
  2. 2026LLaDA-o: An Effective and Length-Adaptive Omni Diffusion Model
  3. 2024Dual Diffusion for Unified Image Generation and Understanding
  4. 2026LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model
  5. 2025ViewMask-1-to-3: Multi-View Consistent Image Generation via Multimodal Discrete Diffusion Models
  6. 2026UniDDT: Unifying Multimodal Understanding and Generation with Decoupled Diffusion Transformer
  7. 2024UNIMO-G: Unified Image Generation through Multimodal Conditional Diffusion
  8. 2025E-MMDiT: Revisiting Multimodal Diffusion Transformer Design for Fast Image Synthesis under Limited Resources